Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A computer-implemented method of providing promotional content related to one or more natural language utterances and/or responses, the method being implemented by a computer system that includes one or more physical processors executing one or more computer program instructions which, when executed, perform the method, the method comprising: receiving, at the one or more physical processors, a first natural language utterance; providing, by the one or more physical processors, a response to the first natural language utterance; receiving, at the one or more physical processors, a second natural language utterance relating to the first natural language utterance; performing, by the one or more physical processors, speech recognition to recognize one or more words of the second natural language utterance; determining, by the one or more physical processors, domain information for the one or more recognized words based on the first natural language utterance; processing, by the one or more physical processors, based on the domain information, the one or more recognized words to determine an interpretation of the second natural language utterance, wherein processing the one or more recognized words comprises: providing the one or more recognized words to a first domain agent associated with a first domain and a second domain agent associated with a second domain; obtaining a first interpretation of the second natural language utterance from the first domain agent; obtaining a second interpretation of the second natural language utterance from the second domain agent; and determining the interpretation based on one or more of the first interpretation or the second interpretation; determining, by the one or more physical processors, promotional content based on the interpretation; and presenting, by the one or more physical processors, the promotional content to a user.
A computer system delivers targeted ads based on voice recognition. It receives a first voice command, responds to it, then receives a second voice command related to the first. Speech recognition is performed on the second command. The system then determines the relevant context (domain) of the recognized words based on the initial command. To interpret the second command, it sends the words to multiple domain-specific agents (e.g., a sports agent and a weather agent), gets interpretations from each, and then determines the final interpretation based on these. Finally, it selects and presents promotional content (ads) to the user based on this interpretation.
2. The method of claim 1 , wherein the first natural language utterance and the second natural language utterance are received during an interactive session between the user and the computer system, the method further comprising: determining, by the one or more physical processors, an activity relating to one or more of the first natural language utterance or the second natural language utterance, wherein determining the promotional content comprises determining the promotional content based on the activity.
If the first and second voice commands occur during an interactive session with the computer, the system, using the method described in claim 1, also determines the activity or goal associated with the voice commands (e.g., playing music, navigation). The promotional content (ads) are then selected based on this determined activity. This ensures the ads are relevant to what the user is currently doing during the interactive session.
3. The method of claim 1 , further comprising: determining, by the one or more physical processors, context information for the one or more recognized words based on the first natural language utterance, wherein the interpretation is determined further based on the context information.
The system, using the method described in claim 1, also determines the broader context surrounding the recognized words from the second voice command, using information from the first voice command (e.g., location, time of day). This context is then used in addition to domain information to determine the interpretation of the second voice command, allowing for more precise ad targeting.
4. The method of claim 1 , wherein the first interpretation is determined by the first domain agent based on the first domain, and wherein the second interpretation is determined by the second domain agent based on the second domain.
In the method described in claim 1, the first domain agent generates its interpretation based solely on the rules and information associated with its domain, while the second domain agent generates its interpretation based on its own, separate domain. This allows for multiple expert interpretations of the same voice command, even if the domains are unrelated.
5. The method of claim 1 , further comprising: associating, by the one or more physical processors, the first interpretation with a first interpretation score; and associating, by the one or more physical processors, the second interpretation with a second interpretation score, wherein determining the interpretation comprises determining the first interpretation as the interpretation based on the first interpretation score and the second interpretation score.
Using the method of claim 1, the system assigns a score to each domain-specific interpretation of the second voice command. The interpretation with the higher score is selected as the final interpretation, which then determines the presented promotional content (ads). This scoring mechanism allows the system to weigh the likelihood of each interpretation being correct.
6. The method of claim 5 , wherein the first interpretation is determined as the interpretation based on the first interpretation score being greater than the second interpretation score.
As described in claim 5, the interpretation from the domain agent that receives the higher score is chosen as the final interpretation. This selection determines which promotional content (ad) will be presented to the user, based on the interpretation that is considered most likely.
7. The method of claim 1 , further comprising: receiving, at the one or more physical processors, a third natural language utterance relating to one or more of the first natural language utterance or the second natural language utterance; and determining, by the one or more physical processors, an interpretation of the third natural language utterance based on the promotional content.
After presenting the promotional content (ad) using the method of claim 1, the system receives a third voice command from the user, related to the previous commands. It then determines an interpretation of this third command, and importantly, this interpretation is influenced by the content of the previously presented promotional content (ad). This allows the system to understand if the user interacted with or acknowledged the ad.
8. The method of claim 7 , wherein the first natural language utterance, the second natural language utterance, and the third natural language utterance are received during an interactive session between the user and the computer system.
In the scenario described in claim 7, all three voice commands (first, second, and third) occur during an interactive session between the user and the computer system. The entire conversation, including the user's response to the promotional content, takes place within a single session.
9. The method of claim 8 , wherein the third natural language utterance is received after the second natural language utterance.
As mentioned in claim 8, the system has an ongoing interactive session. The third voice command, which is related to the promotional content, is received specifically after the second voice command has been processed and the ad has been displayed. This temporal order is important for understanding the user's intent in relation to the ad.
10. The method of claim 7 , further comprising: performing, by the one or more physical processors, speech recognition to recognize one or more words of the third natural language utterance, wherein the one or more recognized words of the third natural language utterance include one or more reference words; determining, by the one or more physical processors, that the one or more reference words refer to an item associated with the promotional content; and initiating, by the one or more physical processors, a purchase transaction associated with the item based on the determination that the one or more reference words refer to the item.
In the method of claim 7, speech recognition is performed on the third voice command. The words recognized from this third command include reference words (e.g., "that," "it"). The system determines if these reference words refer to an item associated with the presented promotional content (ad). If so, the system automatically initiates a purchase transaction for that item.
11. The method of claim 10 , wherein the item includes a purchasable good.
As detailed in claim 10, the item being referenced in the third voice command and automatically purchased is specifically a purchasable good, such as a product or service being advertised in the promotional content.
12. The method of claim 7 , further comprising: initiating, by the one or more physical processors, based on the interpretation of the third natural language utterance, a purchase transaction associated with the promotional content.
Building upon claim 7, after interpreting the third voice command based on the presented promotional content (ad), the system directly initiates a purchase transaction associated with the promotional content, based solely on the interpretation. No explicit reference words are required; the intent to purchase is inferred from the command's meaning within the context of the ad.
13. The method of claim 1 , wherein the first natural language utterance and the second natural language utterance are received during an interactive session between the user and the computer system, the method further comprising: receiving, at the one or more physical processors, a third natural language utterance during the interactive session; and processing, by the one or more physical processors, based on the third natural language utterance, the one or more recognized words to determine a reinterpretation of the second natural language utterance.
During an interactive session with the user, as per claim 1, the system receives a third voice command. Based on this third utterance, the system re-analyzes and updates its interpretation of the second voice command. This "reinterpretation" allows the system to refine its understanding based on new information provided by the user.
14. The method of claim 13 , wherein determining the promotional content comprises determining the promotional content based on the reinterpretation.
As described in claim 13, if the system reinterprets the second voice command based on the third voice command, then the promotional content (ads) are selected and presented based on this new "reinterpretation" instead of the original interpretation.
15. The method of claim 13 , wherein determining the promotional content comprises determining the promotional content based on the interpretation, the method further comprising: determining, by the one or more physical processors, other promotional content based on the reinterpretation; and presenting, by the one or more physical processors, the other promotional content to the user.
The method of claim 13 uses both the original interpretation and the reinterpretation of the second voice command. The initial promotional content (ad) is determined using the first interpretation. Then, based on the reinterpretation driven by the third voice command, *additional* promotional content is determined and presented to the user. The user thus sees two different ads based on their evolving interaction.
16. The method of claim 1 , further comprising: identifying, by the one or more physical processors, one or more requests associated with the second natural language utterance, wherein determining the promotional content comprises obtaining the promotional content based on a determination that the promotional content relates to the one or more requests.
In the method of claim 1, the system identifies one or more requests embedded within the user's second voice command (e.g., "play music," "find a restaurant"). The promotional content (ad) selected is then specifically related to these identified requests. This ensures the ad is contextually relevant to the user's immediate needs.
17. The method of claim 16 , further comprising: determining, by the one or more physical processors, one or more activities in the one or more requests; and performing, by the one or more physical processors, the one or more activities, wherein determining the promotional content comprises determining the promotional content based on the one or more activities.
Expanding upon claim 16, the system determines specific activities or actions implied by the requests (e.g., making a phone call, navigating to a location). The system then *performs* these actions for the user and determines the promotional content (ad) based on the activities being performed. This enables ads to be targeted to specific actions taken by the system.
18. The method of claim 17 , wherein determining the one or more activities comprises determining a call to be initiated for the user in response to the one or more requests, wherein performing the one or more activities comprises initiating the call for the user, and wherein determining the promotional content comprises determining the promotional content based on the call.
Building on claim 17, the system recognizes a request to initiate a phone call and automatically makes the call for the user. The promotional content (ad) presented to the user is specifically related to the phone call (e.g., services related to the contact, phone accessories).
19. The method of claim 17 , wherein determining the one or more activities comprises determining a navigation route to be calculated for the user in response to the one or more requests, wherein performing the one or more activities comprises calculating the navigation route for the user, and wherein determining the promotional content comprises determining the promotional content based on the navigation route.
Building on claim 17, if the user requests navigation, the system calculates the route for the user. The promotional content (ad) that is determined relates specifically to the generated navigation route (e.g. gas stations, restaurants on the way).
20. The method of claim 17 , wherein determining the one or more activities comprise determining a media item to be presented in response to the one or more requests, wherein performing the one or more activities comprises presenting the media item to the user, and wherein determining the promotional content comprises determining the promotional content based on the media item, the promotional content being different than the media item.
Building on claim 17, if the user requests a media item (e.g., a song), the system presents the media item. The promotional content (ad) that is presented is *different* from the media item, but still related to it (e.g., related artists, concert tickets).
21. The method of claim 17 , wherein determining the one or more activities comprises determining a reservation to be made on behalf of the user in response to the one or more requests, and wherein determining the promotional content comprises determining the promotional content based on information relating to the reservation.
Building on claim 17, the system determines that a reservation needs to be made and proceeds to make it. The promotional content presented is based on the details of the reservation (e.g., a hotel booking leads to car rental ads).
22. The method of claim 17 , wherein determining the one or more activities comprises determining a first reservation to be made on behalf of the user in response to the one or more requests, and wherein determining the promotional content comprises determining the promotional content based on information relating to a second reservation that is an alternative to the first reservation.
As in claim 17, the system makes a reservation. But the promotional content shown is related to a *different* reservation, specifically one that serves as an alternative to the user's first reservation (e.g., showing ads for a different hotel, because the first is sold out).
23. The method of claim 17 , further comprising: receiving, at the one or more physical processors, a third natural language utterance relating to one or more of the first natural language utterance or the second natural language utterance; determining, by the one or more physical processors, an interpretation of the third natural language utterance based on the promotional content; and initiating, by the one or more physical processors, based on the interpretation of the third natural language utterance, a purchase transaction associated with the promotional content.
In the method of claim 16, the system receives a third voice command related to the previous commands and promotional content (ad). It then interprets the meaning of this third command, influenced by the promotional content shown. Finally, based on this interpretation, the system initiates a purchase transaction related to the ad.
24. The method of claim 16 , further comprising: determining, by the one or more physical processors, that at least one request of the one or more requests is incomplete or ambiguous; monitoring, by the one or more physical processors, interaction of the user with the promotional content; and interpreting, by the one or more physical processors, the at least one incomplete or ambiguous request based on the interaction.
In claim 16, if the identified request(s) in the user's second voice command are incomplete or ambiguous, the system presents promotional content (ads) related to these requests. It then monitors the user's interactions with the ads (e.g., clicks, views) and uses this interaction data to better understand and interpret the original, ambiguous request.
25. The method of claim 16 , wherein the one or more requests include a first request associated with a first application and a second request associated with a second application different than the first application, and wherein the promotional content relates to one or more of the first request or the second request.
As in claim 16, the user's requests involve multiple applications. One request is for a first application (e.g., navigation), and a second request is for a *different* application (e.g., music). The promotional content (ad) presented can be related to either or both of these different application requests.
26. The method of claim 25 , wherein a first application type of the first application includes one or more of a navigation application, a music application, a commerce application, or a calling application, and wherein the second application is of an application type different than the first application type.
Building on claim 25, the first application can be a navigation, music, commerce, or calling application. The second application *must* be of a different type than the first. For example, if the first request involves navigation, the second request cannot also involve navigation.
27. The method of claim 16 , wherein the one or more requests include a first request to be processed by a first device associated with the user and a second request to be processed by a second device associated with the user, and wherein the promotional content relates to one or more of the first request or the second request.
In the method described in claim 16, the user's requests involve multiple devices. One request is intended for a first device, and another request is intended for a *different* second device belonging to the user. The promotional content can then be related to either or both of these devices.
28. The method of claim 27 , wherein a first device type of the first device includes one or more of a mobile phone, a navigation device, or a media player device, and wherein the second device is of a device type different than the first device type.
As in claim 27, the first device can be a mobile phone, a navigation device, or a media player. The second device must be of a *different* type. For example, if the first request targets the user's mobile phone, the second request cannot target another mobile phone.
29. The method of claim 27 , wherein the first device and the second device are operably independent of one another.
As in claim 27, the first and second devices operate independently from each other. This means they are not directly connected or dependent on each other's functionality, allowing for requests and ads to be targeted across disparate devices.
30. The method of claim 1 , further comprising: obtaining, by the one or more physical processors, user profile information associated with the user, wherein the user profile information specifies prior user interactions with items; and identifying, by the one or more physical processors, categories of items based on the prior user interactions specified by the user profile information, wherein determining the promotional content comprises determining a promotional item associated with one of the categories.
In the method of claim 1, the system uses user profile information that contains a history of user interactions with different items. The system identifies categories of items the user has previously interacted with and then determines promotional content (ads) that are associated with those categories. This personalizes ads based on past behavior.
31. The method of claim 1 , further comprising: obtaining, by the one or more physical processors, user profile information associated with the user, wherein the user profile information specifies prior user interactions with items; identifying, by the one or more physical processors, one or more requests associated with the first natural language utterance or the second natural language utterance; determining, by the one or more physical processors, one or more applications for processing the one or more requests; and identifying, by the one or more physical processors, categories of items based on the prior user interactions specified by the user profile information, wherein the categories relate to the one or more applications, wherein determining the promotional content comprises determining a promotional item associated with one of the categories.
In the method of claim 1, the system combines user profile information (containing a history of user interactions), identified requests from the voice commands, and the applications that are relevant to fulfilling those requests. Categories of items the user has interacted with are determined in the *context* of those applications. Then, the promotional content (ads) presented are selected from those categories.
32. A system for providing promotional content related to one or more natural language utterances and/or responses, the system comprising: one or more physical processors programmed to execute one or more computer program instructions which, when executed, cause the one or more physical processors to: receive a first natural language utterance; provide a response to the first natural language utterance; receive a second natural language utterance relating to the first natural language utterance; perform speech recognition to recognize one or more words of the second natural language utterance; determine domain information for the one or more recognized words based on the first natural language utterance; process, based on the domain information, the one or more recognized words to determine an interpretation of the second natural language utterance, wherein processing the one or more recognized words comprises: providing the one or more recognized words to a first domain agent associated with a first domain and a second domain agent associated with a second domain; obtaining a first interpretation of the second natural language utterance from the first domain agent; obtaining a second interpretation of the second natural language utterance from the second domain agent; and determining the interpretation based on one or more of the first interpretation or the second interpretation; determine promotional content based on the interpretation; and present the promotional content to a user.
A computer system delivers targeted ads based on voice recognition. It receives a first voice command, responds to it, then receives a second voice command related to the first. Speech recognition is performed on the second command. The system then determines the relevant context (domain) of the recognized words based on the initial command. To interpret the second command, it sends the words to multiple domain-specific agents (e.g., a sports agent and a weather agent), gets interpretations from each, and then determines the final interpretation based on these. Finally, it selects and presents promotional content (ads) to the user based on this interpretation. This claim describes a SYSTEM, not a METHOD.
33. A computer-implemented method of providing promotional content related to one or more natural language utterances and/or responses, the method being implemented by a computer system that includes one or more physical processors executing one or more computer program instructions which, when executed, perform the method, the method comprising: receiving, at the one or more physical processors, a first natural language utterance during an interactive session between a user and the computer system; providing, by the one or more physical processors, a response to the first natural language utterance; receiving, at the one or more physical processors, a second natural language utterance relating to the first natural language utterance during the interactive session; performing, by the one or more physical processors, speech recognition to recognize one or more words of the second natural language utterance; processing, by the one or more physical processors, based on the first natural language utterance, the one or more recognized words to determine an interpretation of the second natural language utterance; receiving, at the one or more physical processors, a third natural language utterance during the interactive session; processing, by the one or more physical processors, based on the third natural language utterance, the one or more recognized words to determine a reinterpretation of the second natural language utterance; determining, by the one or more physical processors, promotional content based on one or more of the interpretation or the reinterpretation; and presenting, by the one or more physical processors, the promotional content to the user.
During an interactive session, the system receives a first voice command and responds. It then receives a second voice command relating to the first. Speech recognition is performed on the second command, and the command is initially interpreted. Next, the system receives a third voice command, and *reinterprets* the second command based on this third command. Finally, promotional content (ads) are determined based on *either* the initial interpretation or the reinterpretation and presented to the user.
34. The method of claim 33 , wherein determining the promotional content comprises determining the promotional content based on the reinterpretation.
In the method of claim 33, the promotional content (ad) presented to the user is based solely on the *reinterpretation* of the second voice command, which was informed by the third voice command. The initial interpretation of the second command is not used.
35. The method of claim 33 , wherein determining the promotional content comprises determining the promotional content based on the interpretation, the method further comprising: determining, by the one or more physical processors, other promotional content based on the reinterpretation; and presenting, by the one or more physical processors, the other promotional content to the user.
In the method of claim 33, the initial interpretation of the second voice command is used to determine an initial promotional content (ad) for the user. Then, based on the *reinterpretation* of the second voice command (informed by the third command), *additional* promotional content is determined and also presented to the user.
36. A system for providing promotional content related to one or more natural language utterances and/or responses, the system comprising: one or more physical processors programmed to execute one or more computer program instructions which, when executed, cause the one or more physical processors to: receive a first natural language utterance during an interactive session between a user and the system; provide a response to the first natural language utterance; receive a second natural language utterance relating to the first natural language utterance during the interactive session; perform speech recognition to recognize one or more words of the second natural language utterance; process, based on the first natural language utterance, the one or more recognized words to determine an interpretation of the second natural language utterance; receive a third natural language utterance during the interactive session; process, based on the third natural language utterance, the one or more recognized words to determine a reinterpretation of the second natural language utterance; determine promotional content based on one or more of the interpretation or the reinterpretation; and present the promotional content to the user.
During an interactive session, the system receives a first voice command and responds. It then receives a second voice command relating to the first. Speech recognition is performed on the second command, and the command is initially interpreted. Next, the system receives a third voice command, and *reinterprets* the second command based on this third command. Finally, promotional content (ads) are determined based on *either* the initial interpretation or the reinterpretation and presented to the user. This describes a SYSTEM, not a METHOD.
37. A computer-implemented method of providing promotional content related to one or more natural language utterances and/or responses, the method being implemented by a computer system that includes one or more physical processors executing one or more computer program instructions which, when executed, perform the method, the method comprising: receiving, at the one or more physical processors, a first natural language utterance; providing, by the one or more physical processors, a response to the first natural language utterance; receiving, at the one or more physical processors, a second natural language utterance relating to the first natural language utterance; identifying, by the one or more physical processors, one or more requests associated with the second natural language utterance; determining, by the one or more physical processors, that at least one request of the one or more requests is incomplete or ambiguous; determining, by the one or more physical processors, promotional content that relates to the one or more requests; presenting, by the one or more physical processors, the promotional content to a user; monitoring, by the one or more physical processors, interaction of the user with the promotional content; and interpreting, by the one or more physical processors, the at least one incomplete or ambiguous request based on the interaction.
The system receives a first voice command and responds. Then, it receives a second voice command and identifies one or more requests embedded in it. The system determines that at least one of these requests is incomplete or ambiguous. The system then presents promotional content (ads) that are related to these requests, monitors the user's interaction with the ads, and finally, uses this interaction to interpret the incomplete or ambiguous request.
38. A system for providing promotional content related to one or more natural language utterances and/or responses, the system comprising: one or more physical processors programmed to execute one or more computer program instructions which, when executed, cause the one or more physical processors to: receive a first natural language utterance; provide a response to the first natural language utterance; receive a second natural language utterance relating to the first natural language utterance; identify one or more requests associated with the second natural language utterance; determine that at least one request of the one or more requests is incomplete or ambiguous; determine promotional content that relates to the one or more requests; present the promotional content to a user; monitor interaction of the user with the promotional content; and interpret the at least one incomplete or ambiguous request based on the interaction.
The system receives a first voice command and responds. Then, it receives a second voice command and identifies one or more requests embedded in it. The system determines that at least one of these requests is incomplete or ambiguous. The system then presents promotional content (ads) that are related to these requests, monitors the user's interaction with the ads, and finally, uses this interaction to interpret the incomplete or ambiguous request. This describes a SYSTEM, not a METHOD.
39. A computer-implemented method of providing promotional content related to one or more natural language utterances and/or responses, the method being implemented by a computer system that includes one or more physical processors executing one or more computer program instructions which, when executed, perform the method, the method comprising: receiving, at the one or more physical processors, a first natural language utterance; providing, by the one or more physical processors, a response to the first natural language utterance; receiving, at the one or more physical processors, a second natural language utterance relating to the first natural language utterance; identifying, by the one or more physical processors, requests associated with the second natural language utterance, wherein the requests include a first request associated with a first application and a second request associated with a second application different than the first application; determining, by the one or more physical processors, promotional content that relates to one or more of the first request or the second request; and presenting, by the one or more physical processors, the promotional content to a user.
The system receives a first voice command and responds. Then, it receives a second voice command and identifies requests associated with it. These requests include a request for a first application *and* a request for a *different* second application. The system then determines and presents promotional content (ads) that relate to either the first application request, the second application request, or both.
40. The method of 39 , wherein a first application type of the first application includes one or more of a navigation application, a music application, a commerce application, or a calling application, and wherein the second application is of an application type different than the first application type.
As in claim 39, the first application can be a navigation, music, commerce, or calling application. The second application *must* be of a different type than the first application. For example, the user can request navigation assistance from a navigation app and then request music from a music app.
41. The method of claim 39 , further comprising: receiving, at the one or more physical processors, a third natural language utterance relating to one or more of the first natural language utterance or the second natural language utterance; and determining, by the one or more physical processors, an interpretation of the third natural language utterance based on the promotional content.
Using the method described in claim 39, the system then receives a third voice command that is related to the prior commands or the promotional content shown. The system then determines an interpretation of this third command, specifically taking into account the previously presented promotional content (ad).
42. The method of claim 41 , further comprising: initiating, by the one or more physical processors, based on the interpretation of the third natural language utterance, a purchase transaction associated with the promotional content.
As in claim 41, after interpreting the third voice command in light of the promotional content shown, the system initiates a purchase transaction related to the promotional content. The user's intent to purchase is derived from their third command.
43. A system for providing promotional content related to one or more natural language utterances and/or responses, the system comprising: one or more physical processors programmed to execute one or more computer program instructions which, when executed, cause the one or more physical processors to: receive a first natural language utterance; provide a response to the first natural language utterance; receive a second natural language utterance relating to the first natural language utterance; identify requests associated with the second natural language utterance, wherein the requests include a first request associated with a first application and a second request associated with a second application different than the first application; determine promotional content that relates to one or more of the first request or the second request; and present the promotional content to a user.
The system receives a first voice command and responds. Then, it receives a second voice command and identifies requests associated with it. These requests include a request for a first application *and* a request for a *different* second application. The system then determines and presents promotional content (ads) that relate to either the first application request, the second application request, or both. This describes a SYSTEM, not a METHOD.
44. A computer-implemented method of providing promotional content related to one or more natural language utterances and/or responses, the method being implemented by a computer system that includes one or more physical processors executing one or more computer program instructions which, when executed, perform the method, the method comprising: receiving, at the one or more physical processors, a first natural language utterance; providing, by the one or more physical processors, a response to the first natural language utterance; receiving, at the one or more physical processors, a second natural language utterance relating to the first natural language utterance; identifying, by the one or more physical processors, requests associated with the second natural language utterance, wherein the requests include a first request to be processed by a first device associated with a user and a second request to be processed by a second device associated with the user; determining, by the one or more physical processors, promotional content that relates to one or more of the first request or the second request; and presenting, by the one or more physical processors, the promotional content to the user.
The system receives a first voice command and responds. Then, it receives a second voice command and identifies requests associated with it. These requests include a request intended for a first device associated with the user *and* a request intended for a *different* second device associated with the user. The system then determines and presents promotional content (ads) that relate to either or both device requests.
45. The method of claim 44 , wherein a first device type of the first device includes one or more of a mobile phone, a navigation device, or a media player device, and wherein the second device is of a device type different than the first device type.
As described in claim 44, the first device can be a mobile phone, a navigation device, or a media player. The second device *must* be of a different device type. For example, a user can request something from their mobile phone, and something else from their navigation device.
46. The method of claim 44 , wherein the first device and the second device are operably independent of one another.
As described in claim 44, the first and second devices operate independently of each other. The requests and promotional content can be targeted across devices that are not directly connected or reliant on each other.
47. The method of claim 44 , further comprising: receiving, at the one or more physical processors, a third natural language utterance relating to one or more of the first natural language utterance or the second natural language utterance; and determining, by the one or more physical processors, an interpretation of the third natural language utterance based on the promotional content.
Using the method described in claim 44, after presenting the promotional content (ad), the system receives a third voice command that relates to the prior commands or the ad. It then determines an interpretation of this third command, specifically taking into account the presented promotional content.
48. The method of claim 47 , further comprising: initiating, by the one or more physical processors, based on the interpretation of the third natural language utterance, a purchase transaction associated with the promotional content.
As in claim 47, the system, after interpreting the third voice command in relation to the promotional content (ad), initiates a purchase transaction that is related to the promotional content.
49. A system for providing promotional content related to one or more natural language utterances and/or responses, the system comprising: one or more physical processors programmed to execute one or more computer program instructions which, when executed, cause the one or more physical processors to: receive a first natural language utterance; provide a response to the first natural language utterance; receive a second natural language utterance relating to the first natural language utterance; identify requests associated with the second natural language utterance, wherein the requests include a first request to be processed by a first device associated with a user and a second request to be processed by a second device associated with the user; determine promotional content that relates to one or more of the first request or the second request; and present the promotional content to the user.
The system receives a first voice command and responds. Then, it receives a second voice command and identifies requests associated with it. These requests include a request intended for a first device associated with the user *and* a request intended for a *different* second device associated with the user. The system then determines and presents promotional content (ads) that relate to either or both device requests. This claim describes a SYSTEM, not a METHOD.
50. A computer-implemented method of providing promotional content related to one or more natural language utterances and/or responses, the method being implemented by a computer system that includes one or more physical processors executing one or more computer program instructions which, when executed, perform the method, the method comprising: receiving, at the one or more physical processors, a first natural language utterance; providing, by the one or more physical processors, a response to the first natural language utterance; receiving, at the one or more physical processors, a second natural language utterance relating to the first natural language utterance; obtaining, by the one or more physical processors, user profile information associated with a user, wherein the user profile information specifies prior user interactions with items; identifying, by the one or more physical processors, categories of items based on the prior user interactions specified by the user profile information; determining, by the one or more physical processors, based on the first natural language utterance and the second natural language utterance, promotional content associated with one of the categories; and presenting, by the one or more physical processors, the promotional content to the user.
The system receives a first voice command and responds. Then, it receives a second related voice command. The system then obtains user profile information detailing past interactions with various items. It identifies categories of items based on these past interactions. Finally, the system determines promotional content (ads) from these categories and presents them to the user, targeting ads based on user history and current commands.
51. The method of claim 50 , further comprising: receiving, at the one or more physical processors, a third natural language utterance relating to one or more of the first natural language utterance or the second natural language utterance; and determining, by the one or more physical processors, an interpretation of the third natural language utterance based on the promotional content.
In the method of claim 50, after presenting promotional content (ads), the system receives a third voice command related to the previous commands or the ad. The system then determines an interpretation of this third command, taking the previously presented promotional content into account.
52. The method of claim 51 , further comprising: initiating, by the one or more physical processors, based on the interpretation of the third natural language utterance, a purchase transaction associated with the promotional content.
As described in claim 51, the system interprets the third voice command in relation to the presented promotional content (ad) and then initiates a purchase transaction based on this interpretation, allowing the user to purchase the advertised item through voice command.
53. A system for providing promotional content related to one or more natural language utterances and/or responses, the system comprising: one or more physical processors programmed to execute one or more computer program instructions which, when executed, cause the one or more physical processors to: receive a first natural language utterance; provide a response to the first natural language utterance; receive a second natural language utterance relating to the first natural language utterance; obtain user profile information associated with a user, wherein the user profile information specifies prior user interactions with items; identify categories of items based on the prior user interactions specified by the user profile information; determine, based on the first natural language utterance and the second natural language utterance, promotional content associated with one of the categories; and present the promotional content to the user.
The system receives a first voice command and responds. Then, it receives a second related voice command. The system then obtains user profile information detailing past interactions with various items. It identifies categories of items based on these past interactions. Finally, the system determines promotional content (ads) from these categories and presents them to the user, targeting ads based on user history and current commands. This describes a SYSTEM, not a METHOD.
54. A computer-implemented method of providing promotional content related to one or more natural language utterances and/or responses, the method being implemented by a computer system that includes one or more physical processors executing one or more computer program instructions which, when executed, perform the method, the method comprising: receiving, at the one or more physical processors, a first natural language utterance; providing, by the one or more physical processors, a response to the first natural language utterance; receiving, at the one or more physical processors, a second natural language utterance relating to the first natural language utterance; obtaining, by the one or more physical processors, user profile information associated with a user, wherein the user profile information specifies prior user interactions with items; identifying, by the one or more physical processors, one or more requests associated with one or more of the first natural language utterance or the second natural language utterance; determining, by the one or more physical processors, one or more applications for processing the one or more requests; and identifying, by the one or more physical processors, categories of items based on the prior user interactions specified by the user profile information, wherein the categories relate to the one or more applications; determining, by the one or more physical processors, based on the first natural language utterance and the second natural language utterance, promotional content associated with one of the categories; and presenting, by the one or more physical processors, the promotional content to the user.
The system receives a first voice command and responds. Then, it receives a second related voice command. The system obtains user profile information detailing past user interactions. It identifies requests in the voice commands and the applications used to fulfill those requests. The system then identifies categories of items based on past user interactions *specifically related to these applications.* Promotional content (ads) are selected from these categories, presenting targeted ads based on history, context, and application.
55. A system for providing promotional content related to one or more natural language utterances and/or responses, the system comprising: one or more physical processors programmed to execute one or more computer program instructions which, when executed, cause the one or more physical processors to: receive a first natural language utterance; provide a response to the first natural language utterance; receive a second natural language utterance relating to the first natural language utterance; obtain user profile information associated with a user, wherein the user profile information specifies prior user interactions with items; identify one or more requests associated with one or more of the first natural language utterance or the second natural language utterance; determine one or more applications for processing the one or more requests; and identify categories of items based on the prior user interactions specified by the user profile information, wherein the categories relate to the one or more applications; determine, based on the first natural language utterance and the second natural language utterance, promotional content associated with one of the categories; and present the promotional content to the user.
The system receives a first voice command and responds. Then, it receives a second related voice command. The system obtains user profile information detailing past user interactions. It identifies requests in the voice commands and the applications used to fulfill those requests. The system then identifies categories of items based on past user interactions *specifically related to these applications.* Promotional content (ads) are selected from these categories, presenting targeted ads based on history, context, and application. This describes a SYSTEM, not a METHOD.
Unknown
November 11, 2014
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.